Active Bones, Joints & Muscles Computing & AI

Real-world testing of software for measuring bone disease on whole-body MRI in patients with prostate cancer and myeloma

In plain English

AI plain-English summary

A new computer software could let doctors measure bone tumours from whole-body MRI scans in minutes instead of hours. Why this matters – Doctors currently assess bone disease in prostate cancer and myeloma by visually comparing scans, which is slow and subjective. The software automatically calculates total disease volume and a measure of water movement in tissue (ADC), giving objective numbers that could track whether a tumour is growing or shrinking. The team will test this software in two clinical trials—one for prostate cancer, one for myeloma—and evaluate whether it leads to faster, more confident diagnoses. Potential impact – If the trials show the software works reliably, it could standardise how the NHS monitors bone disease, replacing inconsistent visual assessments with automated measurements. Radiologists would spend less time on manual analysis and more on clinical decisions. The researchers will also model costs and explore commercial pathways, aiming to make the tool affordable for routine NHS use. For patients, this could mean quicker detection of disease progression and more timely treatment adjustments.

View original technical description
Research question Can using WBMRI and our novel software result in faster, more accurate and/or more confident disease assessment compared with conventional pathways in patients with bone disease from advanced prostate cancer and myeloma? Background WBMRI is useful for assessing bone disease extent and response to treatment by measuring the total disease volume (tDV) and apparent diffusion coefficient (ADC), but requires software to quantify these for clinical application. We have developed a CE-labelled software which can automatically measure the tDV and ADC from WBMRI to assess bone disease. Aims and objectives The aim is to test the real-world performance of our CE-labelled computer software with WBMRI to measure bone disease, by assessing its clinical performance, identify barriers to adoption, and roadmap its wider adoption. The objectives are to: (1) map the interactions of our software with stakeholders; (2) validate use of training for doctors to promote technology uptake; (3) test the performance of WBMRI and software for assessing bone disease response to treatment in prostate cancer and for diagnosing myeloma; (4) determine costs and cost-effectiveness; and (5) evaluate commercial models for NHS deployment. Methods We will (1) evaluate relevant human factors and software usability to refine product; (2) develop and validate training to utilise WBMRI and software; (3) undertake two clinical trials in advanced prostate cancer and myeloma to determine clinical effectiveness; (4) perform health-economic analysis; and (5) explore commercial models for dissemination. Timelines for delivery WP1 [month 3-39]; WP2 [month 1 to 24]; WP3 [month 7 to 48]; WP4 [month 1-6 and 36-48]; WP5 [1-48]. Anticipated impact and dissemination Improved disease management and outcomes for patients; new diagnostic skills and/or faster reporting for radiologists; increased clinician confidence in decision making; standardised cost-effective WBMRI service for the NHS; investment in the UK contributing to economic growth.

View the original record at the funder ↗

Related Research

Grants with similar aims, by meaning.

Advanced computer diagnostics for whole body magnetic resonance imaging to improve management of patients with metastatic bone cancer
Real-world (WISER-Whole-body MRI); Real-world testing of software for evaluating systemic malignant bone disease on whole-body MRI
WISER-P: Real-world testing of software for measuring bone disease on whole-body MRI in patients with prostate cancer
Development and evaluation of machine learning methods in whole body magnetic resonance imaging with diffusion weighted imaging for staging of patients with cancer. (MAchine Learning In whole Body Oncology, MALIBO)
MAchine Learning In MyelomA Response (MALIMAR study): Development of machine learning support for reading whole body diffusion weighted magnetic resonance imaging (WB-MRI) in myeloma for the detection and quantification of the extent of disease before and after treatment

Original classification

Research

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.